基于改进U-Net CNN架构的眼图像分割方法

Casian Miron, Laura Ioana Grigoras, Radu Ciucu, V. Manta
{"title":"基于改进U-Net CNN架构的眼图像分割方法","authors":"Casian Miron, Laura Ioana Grigoras, Radu Ciucu, V. Manta","doi":"10.2478/bipie-2021-0010","DOIUrl":null,"url":null,"abstract":"Abstract The paper presents a new eye image segmentation method used to extract the pupil contour based on the modified U-Net CNN architecture. The analysis was performed using two databases which contain IR images with a spatial resolution of 640x480 pixels. The first database was acquired in our laboratory and contains 400 eye images and the second database is a selection of 400 images from the publicly available CASIA Iris Lamp database. The results obtained by applying the segmentation based on the CNN architecture were compared to manually-annotated ground truth data. The results obtained are comparable to the state of the art. The purpose of the paper is to present the implementation of a robust segmentation algorithm based on the U-Net convolutional neural network that can be used in eye tracking applications such as human computer interface, communication devices for people with disabilities, marketing research or clinical studies. The proposed method improves uppon existing U-Net CNN architectures in terms of efficiency, by reducing the total number of parameters used from 31 millions to 38k. The advantages of using a number of parameters approximatly 815 times lower than the original U-Net CNN architecture are reduced computing resources consumption and a lower inference time.","PeriodicalId":330949,"journal":{"name":"Bulletin of the Polytechnic Institute of Iași. Electrical Engineering, Power Engineering, Electronics Section","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Eye Image Segmentation Method Based on the Modified U-Net CNN Architecture\",\"authors\":\"Casian Miron, Laura Ioana Grigoras, Radu Ciucu, V. Manta\",\"doi\":\"10.2478/bipie-2021-0010\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract The paper presents a new eye image segmentation method used to extract the pupil contour based on the modified U-Net CNN architecture. The analysis was performed using two databases which contain IR images with a spatial resolution of 640x480 pixels. The first database was acquired in our laboratory and contains 400 eye images and the second database is a selection of 400 images from the publicly available CASIA Iris Lamp database. The results obtained by applying the segmentation based on the CNN architecture were compared to manually-annotated ground truth data. The results obtained are comparable to the state of the art. The purpose of the paper is to present the implementation of a robust segmentation algorithm based on the U-Net convolutional neural network that can be used in eye tracking applications such as human computer interface, communication devices for people with disabilities, marketing research or clinical studies. The proposed method improves uppon existing U-Net CNN architectures in terms of efficiency, by reducing the total number of parameters used from 31 millions to 38k. The advantages of using a number of parameters approximatly 815 times lower than the original U-Net CNN architecture are reduced computing resources consumption and a lower inference time.\",\"PeriodicalId\":330949,\"journal\":{\"name\":\"Bulletin of the Polytechnic Institute of Iași. Electrical Engineering, Power Engineering, Electronics Section\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bulletin of the Polytechnic Institute of Iași. Electrical Engineering, Power Engineering, Electronics Section\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2478/bipie-2021-0010\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bulletin of the Polytechnic Institute of Iași. Electrical Engineering, Power Engineering, Electronics Section","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2478/bipie-2021-0010","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

摘要提出了一种基于改进的U-Net CNN结构提取瞳孔轮廓的眼部图像分割新方法。使用两个数据库进行分析,其中包含空间分辨率为640x480像素的红外图像。第一个数据库是在我们的实验室获得的,包含400张眼睛图像,第二个数据库是从公开的CASIA虹膜灯数据库中选择的400张图像。将基于CNN架构的分割结果与人工标注的地面真值数据进行对比。所获得的结果可与目前的技术水平相媲美。本文的目的是介绍一种基于U-Net卷积神经网络的鲁棒分割算法的实现,该算法可用于眼动追踪应用,如人机界面,残疾人通信设备,市场研究或临床研究。提出的方法在效率方面改进了现有的U-Net CNN架构,将使用的参数总数从3100万减少到38k。使用的参数数量比原来的U-Net CNN架构少约815倍,其优点是减少了计算资源的消耗和更短的推理时间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Eye Image Segmentation Method Based on the Modified U-Net CNN Architecture
Abstract The paper presents a new eye image segmentation method used to extract the pupil contour based on the modified U-Net CNN architecture. The analysis was performed using two databases which contain IR images with a spatial resolution of 640x480 pixels. The first database was acquired in our laboratory and contains 400 eye images and the second database is a selection of 400 images from the publicly available CASIA Iris Lamp database. The results obtained by applying the segmentation based on the CNN architecture were compared to manually-annotated ground truth data. The results obtained are comparable to the state of the art. The purpose of the paper is to present the implementation of a robust segmentation algorithm based on the U-Net convolutional neural network that can be used in eye tracking applications such as human computer interface, communication devices for people with disabilities, marketing research or clinical studies. The proposed method improves uppon existing U-Net CNN architectures in terms of efficiency, by reducing the total number of parameters used from 31 millions to 38k. The advantages of using a number of parameters approximatly 815 times lower than the original U-Net CNN architecture are reduced computing resources consumption and a lower inference time.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信